PollutionNet fuses Sentinel-5P satellite data with ground measurements via Vision Transformer self-attention to predict NO2 and SO2 levels with RMSE of 6.89 and 4.49 μg/m³, cutting errors up to 14% versus baselines.
Advances in Neural Information Processing Systems 36 Rafaj P, Kiesewetter G, G¨ ul T, et al (2018) Outlook for clean air in the context of sustainable development goals
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
PollutionNet: A Vision Transformer Framework for Climatological Assessment of NO$_2$ and SO$_2$ Using Satellite-Ground Data Fusion
PollutionNet fuses Sentinel-5P satellite data with ground measurements via Vision Transformer self-attention to predict NO2 and SO2 levels with RMSE of 6.89 and 4.49 μg/m³, cutting errors up to 14% versus baselines.